{"id":"https://openalex.org/W7128595524","doi":"https://doi.org/10.1007/s44443-026-00550-8","title":"Look, compare and refine: Iterative image-text alignment-driven self-refinement for handwritten mathematical expression recognition","display_name":"Look, compare and refine: Iterative image-text alignment-driven self-refinement for handwritten mathematical expression recognition","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128595524","doi":"https://doi.org/10.1007/s44443-026-00550-8"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-026-00550-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00550-8","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44443-026-00550-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104259287","display_name":"Jinzheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinzheng Liu","raw_affiliation_strings":["Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125606827","display_name":"Ting Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ting Zhang","raw_affiliation_strings":["Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0009-0515-7211","affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125600206","display_name":"Bin He","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125614944","display_name":"Shuai Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yuan","raw_affiliation_strings":["Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125623192","display_name":"Jiayu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayu Chen","raw_affiliation_strings":["Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125616195","display_name":"Xueer Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueer Lin","raw_affiliation_strings":["Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043642303","display_name":"Xinguo Yu","orcid":"https://orcid.org/0000-0001-8379-6742"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinguo Yu","raw_affiliation_strings":["Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence in Education, Central China Normal University, No. 152, Luoyu Road, Hongshan District, Wuhan, 430079, Hubei, China","institution_ids":["https://openalex.org/I40963666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5125606827"],"corresponding_institution_ids":["https://openalex.org/I40963666"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24595719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6783999800682068},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6215000152587891},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5866000056266785},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5422000288963318},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.429500013589859},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.40290001034736633},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.37540000677108765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36390000581741333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882000207901001},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6783999800682068},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5625},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43299999833106995},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.429500013589859},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.40290001034736633},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25220000743865967},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-026-00550-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00550-8","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0795695b001846ec922bda2e8278333a","is_oa":true,"landing_page_url":"https://doaj.org/article/0795695b001846ec922bda2e8278333a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 38, Iss 3 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-026-00550-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00550-8","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W110803930","https://openalex.org/W1588942736","https://openalex.org/W1998768285","https://openalex.org/W2012191176","https://openalex.org/W2164969691","https://openalex.org/W2528252828","https://openalex.org/W2623860192","https://openalex.org/W2785656387","https://openalex.org/W2905413777","https://openalex.org/W2963351448","https://openalex.org/W2963446712","https://openalex.org/W2963637207","https://openalex.org/W3002575754","https://openalex.org/W3004196288","https://openalex.org/W3201757274","https://openalex.org/W4200635795","https://openalex.org/W4312299669","https://openalex.org/W4312868947","https://openalex.org/W4313125865","https://openalex.org/W4322695928","https://openalex.org/W4394748224","https://openalex.org/W4396214504","https://openalex.org/W4401043235","https://openalex.org/W4401414318","https://openalex.org/W4402343071","https://openalex.org/W4402713111","https://openalex.org/W4402959365","https://openalex.org/W4402961917","https://openalex.org/W4402997464","https://openalex.org/W4404566288","https://openalex.org/W4409366157","https://openalex.org/W4409368335","https://openalex.org/W4412888604"],"related_works":[],"abstract_inverted_index":{"Handwritten":[0],"mathematical":[1],"expression":[2,191],"recognition":[3,38],"(HMER)":[4],"is":[5,42,73,244],"a":[6,37,43,59,67,143],"highly":[7],"challenging":[8],"task,":[9],"as":[10],"it":[11,27,99],"involves":[12],"not":[13],"only":[14],"distinguishing":[15],"visually":[16,156],"similar":[17,157],"characters":[18],"but":[19],"also":[20],"interpreting":[21],"complex":[22,51,240],"structures.":[23],"Even":[24],"for":[25,64,234],"humans,":[26],"sometimes":[28],"requires":[29],"several":[30],"rounds":[31],"of":[32,109,200,218],"confirmation":[33],"to":[34,75,151,153],"arrive":[35],"at":[36],"result.":[39],"Iterative":[40],"self-refinement":[41,222],"strategy":[44,146],"frequently":[45],"employed":[46],"by":[47,54,141],"humans":[48],"when":[49],"tackling":[50],"tasks.":[52,241],"Inspired":[53],"this,":[55],"we":[56,134],"put":[57],"forward":[58],"self-reflective,":[60],"closed-loop":[61],"feedback":[62],"architecture":[63],"HMER.":[65],"Specifically,":[66],"compatible":[68],"Confidence-Guided":[69],"Self-Correction":[70],"Module":[71],"(CGSCM)":[72],"proposed":[74,229],"endow":[76],"existing":[77],"end-to-end":[78,176],"HMER":[79,177,226],"models":[80,238],"with":[81,206],"self-correcting":[82],"capabilities.":[83],"CGSCM":[84,172,230],"evaluates":[85],"the":[86,90,95,106,115,129,138,149,163,190,193,207,216,220,225],"semantic":[87],"consistency":[88,108],"between":[89,155],"preceding":[91],"token":[92,144],"predictions":[93],"and":[94,167,204],"original":[96],"handwritten":[97],"image;":[98],"accordingly":[100],"assigns":[101],"confidence":[102],"scores":[103,113],"that":[104,147,171],"reflect":[105],"visual":[107],"each":[110],"token.":[111],"These":[112],"guide":[114],"model":[116,150,182],"in":[117,128,224,239],"rethinking":[118],"its":[119],"previous":[120],"predictions,":[121],"placing":[122],"greater":[123],"emphasis":[124],"on":[125,162],"low-confidence":[126],"tokens":[127],"next":[130],"refinement":[131],"step.":[132],"Furthermore,":[133],"incorporate":[135],"self-correction":[136],"into":[137],"training":[139],"phase":[140],"introducing":[142,219],"replacement":[145],"forces":[148],"learn":[152],"distinguish":[154],"symbols.":[158],"Extensive":[159],"experiments":[160],"conducted":[161],"public":[164],"CROHME,":[165],"HME100K,":[166],"QA-HME":[168],"datasets":[169,203],"demonstrate":[170],"can":[173],"consistently":[174],"enhance":[175],"performance":[178],"across":[179,202],"different":[180],"state-of-the-art":[181],"backbones,":[183,205],"thus":[184],"achieving":[185],"new":[186],"benchmark":[187],"performance.":[188],"Considering":[189],"level,":[192],"accuracy":[194],"has":[195,214],"achieved":[196],"an":[197],"average":[198],"improvement":[199,209],"1.01%":[201],"maximum":[208],"reaching":[210],"2.19%.":[211],"Our":[212],"work":[213],"verified":[215],"effectiveness":[217],"iterative":[221],"mechanism":[223],"task.":[227],"The":[228,242],"provides":[231],"valuable":[232],"insight":[233],"building":[235],"robust":[236],"self-refining":[237],"code":[243],"available":[245],"at:":[246],"https://github.com/Jzliu-dl/CGSCM":[247]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2026-02-11T00:00:00"}
